Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 2714 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.8108. Min Range: -0.8108

Max Act: 0.8108. Min Act: -0.0000

Data Index: 1384500 (The Pile)

Max Activating Token Index: 213

Text #1

Max Range: 0.8108. Min Range: -0.8108

Max Act: 0.7850. Min Act: -0.0000

Data Index: 1864293 (The Pile)

Max Activating Token Index: 414

Text #2

Max Range: 0.8108. Min Range: -0.8108

Max Act: 0.7405. Min Act: -0.0000

Data Index: 1235092 (The Pile)

Max Activating Token Index: 364

Text #3

Max Range: 0.8108. Min Range: -0.8108

Max Act: 0.7459. Min Act: -0.0000

Data Index: 1007853 (The Pile)

Max Activating Token Index: 200

Text #4

Max Range: 0.8108. Min Range: -0.8108

Max Act: 0.7564. Min Act: -0.0000

Data Index: 1302717 (The Pile)

Max Activating Token Index: 984

Text #5

Max Range: 0.8108. Min Range: -0.8108

Max Act: 0.7221. Min Act: -0.0000

Data Index: 1175681 (The Pile)

Max Activating Token Index: 367

Text #6

Max Range: 0.8108. Min Range: -0.8108

Max Act: 0.7201. Min Act: -0.0000

Data Index: 1644665 (The Pile)

Max Activating Token Index: 419

Text #7

Max Range: 0.8108. Min Range: -0.8108

Max Act: 0.6984. Min Act: -0.0000

Data Index: 1489468 (The Pile)

Max Activating Token Index: 199

Text #8

Max Range: 0.8108. Min Range: -0.8108

Max Act: 0.6032. Min Act: -0.0000

Data Index: 383565 (The Pile)

Max Activating Token Index: 978

Text #9

Max Range: 0.8108. Min Range: -0.8108

Max Act: 0.6858. Min Act: -0.0000

Data Index: 1136617 (The Pile)

Max Activating Token Index: 252

Text #10

Max Range: 0.8108. Min Range: -0.8108

Max Act: 0.6676. Min Act: -0.0000

Data Index: 1338101 (The Pile)

Max Activating Token Index: 344

Text #11

Max Range: 0.8108. Min Range: -0.8108

Max Act: 0.6664. Min Act: -0.0000

Data Index: 51930 (The Pile)

Max Activating Token Index: 670

Text #12

Max Range: 0.8108. Min Range: -0.8108

Max Act: 0.6469. Min Act: -0.0000

Data Index: 1339104 (The Pile)

Max Activating Token Index: 836

Text #13

Max Range: 0.8108. Min Range: -0.8108

Max Act: 0.6575. Min Act: -0.0000

Data Index: 785267 (The Pile)

Max Activating Token Index: 567

Text #14

Max Range: 0.8108. Min Range: -0.8108

Max Act: 0.6442. Min Act: -0.0000

Data Index: 359248 (The Pile)

Max Activating Token Index: 972

Text #15

Max Range: 0.8108. Min Range: -0.8108

Max Act: 0.7246. Min Act: -0.0000

Data Index: 1484797 (The Pile)

Max Activating Token Index: 547

Text #16

Max Range: 0.8108. Min Range: -0.8108

Max Act: 0.6388. Min Act: -0.0000

Data Index: 1546397 (The Pile)

Max Activating Token Index: 285

Text #17

Max Range: 0.8108. Min Range: -0.8108

Max Act: 0.6274. Min Act: -0.0000

Data Index: 1685499 (The Pile)

Max Activating Token Index: 771

Text #18

Max Range: 0.8108. Min Range: -0.8108

Max Act: 0.6675. Min Act: -0.0000

Data Index: 1837379 (The Pile)

Max Activating Token Index: 174

Text #19

Max Range: 0.8108. Min Range: -0.8108

Max Act: 0.6281. Min Act: -0.0000

Data Index: 52507 (The Pile)

Max Activating Token Index: 123